Monte Carlo Simulation
A method that draws thousands of possible paths to show a RANGE of outcomes, not one outcome.
A Monte Carlo simulation is a computational technique that, instead of a single forecast, generates thousands of random "walks" of value over time. Each run starts from today's value and, step by step, adds a random return whose distribution is based on historical data: the average return (drift) and the volatility of the asset or portfolio. Because each step is random, some paths climb upward and some fall through a streak of negative draws. That is why simulated portfolio value CAN decline despite a positive average return. From the whole bundle of paths, the distribution of final outcomes is then computed and selected percentiles are shown: the median (p50), a pessimistic scenario (e.g. p10) and an optimistic one (e.g. p90). The width of this "fan" reflects uncertainty: the higher the volatility, the wider the spread. It is a probabilistic illustration of possible ranges based on the past. It is not a forecast, a guarantee or advice, as past volatility does not foretell future volatility.
In plain words
The computer replays your portfolio thousands of times with random swings based on its past volatility. Instead of one number you get a fan: from a worst case to a best case. Some draws turn out badly, which is why some paths fall.
Example
After 1,000 runs the median (p50) lands near today's value, p10 reaches −40% and p90 +90%. A wide fan signals high uncertainty. It is an illustration of possible ranges, not a prediction of a specific outcome.
Also known as: monte carlo, symulacja monte carlo, monte carlo simulation, симуляція монте-карло